sumsub-integrate-msdk

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a bash command to query the latest SDK version using git ls-remote from the vendor's official repository.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to download and integrate frameworks from the vendor's GitHub organization (github.com/sumsub) and the official CocoaPods registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill performs an automated scan of local project files (e.g., Podfile, package.json, .xcodeproj) to customize the integration steps, which creates a surface for processing untrusted data.
  • Ingestion points: The skill reads various project metadata files in the stages/1-scan.md file.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the scanned project files.
  • Capability inventory: The agent is allowed to use Read, Write, Edit, and Bash tools to modify the project based on the input gathered during the scan.
  • Sanitization: No specific content sanitization or validation logic is defined for the data extracted from the user's project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 05:01 AM
Security Audit — agent-trust-hub — sumsub-integrate-msdk